@mmerterden/multi-agent-pipeline 16.21.0 → 16.24.0

package/pipeline/multi-agent-refs/generate-issue.md

@@ -241,11 +241,11 @@ curl -sS -X POST -H "Authorization: Bearer $TOKEN" -H "Content-Type: application
 ```
 4. **Screenshot / image attachments** (only when opted in during preview  -  Figma render and/or user-pasted images):
 ```bash
-curl -sS -X POST -H "Authorization: Bearer $TOKEN" -H "X-Atlassian-Token: no-check" \
-  -F "file=@/tmp/generate-issue-$$-figma.png" \
-  "https://$ACCOUNT_JIRA_HOST/rest/api/2/issue/${NEW_KEY}/attachments"
+bash "$HOME/.claude/scripts/jira-attach.sh" "$NEW_KEY" /tmp/generate-issue-$$-figma.png
 ```
 
+One uploader, shared with visual evidence: two copies of this call is two places for `X-Atlassian-Token: no-check` to go missing, which fails as a 403 that reads like an auth problem. It prints `<filename>\t<url>` per file.
+
 ### [12/12] Report
 
 ```

package/pipeline/multi-agent-refs/phases/modes.md

@@ -73,7 +73,7 @@ Bu is icin hangi pipeline? / Which pipeline for this task?
 
 **Who is asked.** `/multi-agent` and `/multi-agent:local`. Both autopilot entries always run Full without asking.
 
-**Why there is no fast-and-unattended combination.** It existed until v16.0.0 as `--dev autopilot`, and removing it is a real behaviour change, not a rename. Autopilot may not ask, so something has to choose, and unattended is the worst place to drop analysis and planning: nobody is watching to notice what the shortcut lost. A cron job or script that called `dev-autopilot` now has to pick - stay unattended and pay for the full pipeline, or stay fast and have a person present.
+**Why there is no fast-and-unattended combination.** It existed until v16.0.0, and removing it was a real behaviour change, not a rename. Autopilot may not ask, so something has to choose, and unattended is the worst place to drop analysis and planning: nobody is watching to notice what the shortcut lost. A cron job or script that wants both now has to pick - stay unattended and pay for the full pipeline, or stay fast and have a person present.
 
 **Pipeline in a Short run:**
 

package/pipeline/multi-agent-refs/phases/phase-0-init.md

@@ -12,16 +12,21 @@ $HOME/.claude/scripts/phase-tracker.sh init "$TASK_ID"
 for p in 0:Init 1:Analysis 2:Planning 3:Dev 4:Review 5:Test 6:Commit 7:Report; do
   $HOME/.claude/scripts/phase-tracker.sh add "${p%%:*}" "${p#*:}"
 done
+$HOME/.claude/scripts/phase-tracker.sh tiles
 $HOME/.claude/scripts/phase-tracker.sh update 0 in_progress
 ```
 
+`tiles` prints this host's widget-registration calls: **make them before continuing.** The card alone lands in collapsed tool output, so a run that skips them runs in silence. Contract: `tracker-contract.md`, "The card is not the widget".
+
 If `INPUT_TASK_ID` isn't known yet (free-text, project not selected), use a placeholder; rename later via `mv` once parsed in Step 1.
 
-Every subsequent phase (1-7) MUST call `phase-tracker.sh update <N> in_progress` on entry and `phase-tracker.sh update <N> completed|failed|skipped` on exit. Sub-phase milestones use `phase-tracker.sh sub <N> <subN> "<name>" <status>`. See `$HOME/.claude/multi-agent-refs/phases.md` "Visual Phase Tracker" for the full contract.
+Every subsequent phase (1-7) MUST call `phase-tracker.sh update <N> in_progress` on entry and `phase-tracker.sh update <N> completed|failed|skipped` on exit. Each `update` prints a `-- NEXT (required) --` block: act on it. Sub-phase milestones use `phase-tracker.sh sub <N> <subN> "<name>" <status>`. See `$HOME/.claude/multi-agent-refs/phases.md` "Visual Phase Tracker" for the full contract.
+
+`update <N> completed` **exits 3** for phases 1-4 with no recorded spend: record `model` + `tokens`, or pass `--no-llm`, then re-run it. Contract: `tracker-contract.md`, "Accounting is a gate".
 
 ##### TaskCreate ordering on Claude Code (strict)
 
-On Claude Code, fire all `TaskCreate` calls in strict phase-number order (0 → 7) BEFORE any `TaskUpdate`. Full contract: `$HOME/.claude/multi-agent-refs/tracker-contract.md` section "TaskCreate ordering (strict)".
+On Claude Code, fire all `TaskCreate` calls in strict phase-number order (0 → 7) BEFORE any `TaskUpdate` - which is the order `tiles` prints them in. Full contract: `$HOME/.claude/multi-agent-refs/tracker-contract.md` section "TaskCreate ordering (strict)".
 
 ---
 
@@ -88,6 +93,8 @@ Probe order:
 1. **Tier 1 (Figma MCP)**: check the host serves `mcp__claude_ai_Figma__*` before probing. Absent → set `state.figmaAccess.tier1Unavailable = "host"` and fall through to Tier 2 with no probe, no re-auth retry, no MCP-token question. Present → probe `get_metadata(fileKey, nodeId)` on the first frame; on auth failure run `authenticate` + `complete_authentication` and retry once, and only a *second* failure raises the recreate-or-continue question. Success → `state.figmaAccess.tier = 1`.
 2. **Tier 2 (Figma REST)**: when Tier 1 fails, resolve the PAT via `~/.claude/lib/credential-store.sh get <logical-key>` where `<logical-key>` = `prefs.global.keychainMapping.figma`. Probe `GET https://api.figma.com/v1/files/{fileKey}/nodes?ids={nodeId}` with header `X-Figma-Token: $TOKEN`. HTTP 200 → `state.figmaAccess.tier = 2`. Token missing / 401 / 403 → fall through.
 3. **Tier 3 (User-attached screenshot)**: when Tiers 1 + 2 both fail, scan the task payload for inline screenshots or attachments. Present → `state.figmaAccess.tier = 3` and `state.figmaAccess.reviewBlocking = true` (Phase 4 enforces this).
+
+Save the issue's image attachments to `$WORKTREE/.pipeline/evidence/` as `state.visualEvidence.before[]`: pre-fix evidence, never re-photographed, and none present is a recorded gap rather than a search. See `$HOME/.claude/multi-agent-refs/features/visual-evidence.md`.
 4. **Halt**: all three tiers fail → emit a single AskUserQuestion asking the user how to proceed (provide PAT, paste a screenshot, abort). Never proceed with text-derived guesses.
 
 Record the cause, not just the downshift. `tier1Unavailable = "host"` means the tier never existed here - routine on Copilot and Codex, where the installer registers only `multi-agent-toolkit`. `"auth"` means it existed and the credential failed, which on Claude Code points at a dead `figma_mcp` token worth surfacing in Phase 7. Conflating them costs two wasted MCP round trips and a question the user cannot act on. On those two hosts a mapped `figma` PAT is the primary path, not a fallback.

package/pipeline/multi-agent-refs/phases/phase-3-dev.md

@@ -234,6 +234,10 @@ Gated by `prefs.global.devCritic.enabled` (default: `false`). When enabled, afte
 
 ---
 
+#### Step 3.55  -  Visual evidence capture (UI changes only)
+
+When `state.visualEvidence.required`, capture the fixed state with the build that just went green: `capture-evidence.sh after --task "$TASK_ID" --platform "$PLATFORM" --label <slug>`. Here, not Phase 5, which every autopilot and `--local` entry drops. Exit 4 is a gap, not a failure. See `$HOME/.claude/multi-agent-refs/features/visual-evidence.md`.
+
 #### Step 3.6  -  Code-simplifier pass (required diff shrink, before Phase 4 handoff)
 
 After the build/test green step and BEFORE Phase 4 handoff, run one diff-shrink round (bloated diffs waste Phase 4 reviewer tokens and unfocus the PR).
@@ -298,7 +302,7 @@ Set by the Phase 0 Step 7.5 depth picker, or by autopilot never (autopilot alway
 
 Because the agent determines its own scope here, Phase 4 is the only place that checks the result against anything external. Record every skill, plugin skill and guide consulted during this phase into `state.telemetry.skillCalls[]` with the files it was applied to  -  Phase 4 resolves the criteria set independently, and this record is what lets it tell "applied and honoured" from "never opened".
 
-**Never combined with autopilot.** Autopilot skips the depth question and runs Full, so `onlyDevelop` is false in every unattended run. "Fast plus unattended" was `--dev autopilot` until v16.0.0 and no longer exists: something has to choose when nobody is asked, and unattended is the worst place to drop analysis and planning.
+**Never combined with autopilot.** Autopilot skips the depth question and runs Full, so `onlyDevelop` is false in every unattended run. "Fast plus unattended" was removed in v16.0.0 and no longer exists: something has to choose when nobody is asked, and unattended is the worst place to drop analysis and planning.
 
 **Tracker visibility during Opus dispatch**: on Claude Code the model switch to Opus happens via subagent dispatch, and the parent widget cannot move while an Agent call is in flight. Dispatch per task from the self-generated task list (never one monolithic call for the whole phase), set the pre-dispatch `activeForm` marker, and record tokens between chunks  -  full rules in `$HOME/.claude/multi-agent-refs/tracker-contract.md` section "Delegated phases".
 

package/pipeline/multi-agent-refs/phases/phase-5-test.md

@@ -138,6 +138,7 @@ Before or during user testing, run device-level audits via Bash if user requests
 
 | Check               | When              | Command                                   |
 | ------------------- | ----------------- | ----------------------------------------- |
+| UI flow video       | `state.visualEvidence.required` | 3 tiers, cap from `capture-evidence.sh limits` (`visualEvidence.maxVideoSeconds`)  -  `$HOME/.claude/multi-agent-refs/features/visual-evidence.md` |
 | Accessibility audit | UI changes        | `mcp__multi-agent-toolkit__{ios,android}_accessibility_audit` |
 | Biometric test      | Auth flow changes | ios: `mcp__multi-agent-toolkit__ios_biometric` (android: manual) |
 | Launch time         | Perf-sensitive changes | ios: app-launch instrument · android: `mcp__multi-agent-toolkit__android_launch_time` |

package/pipeline/multi-agent-refs/phases/phase-6-commit.md

@@ -136,7 +136,7 @@ Branch **deterministically**, no implicit fallback. Read `agent-state.json` and
 
 Generate a structured PR description based on task type. The PR body targets **code reviewers**  -  it should be technical: what changed, why, architecture decisions, how to verify.
 
-Two inputs are read from state and the worktree before writing, not recalled from the conversation: `$WORKTREE/.pipeline/scope-check.json` (Phase 3 Step 3.7) supplies the `## Changes` bullets from `files[].reason` and the "Follow-ups not done in this PR" list under `## Related` from `notDone[]`; `state.diffRisk.signals` (Phase 4 Step 1.75) decides whether the conditional `## Risk and Security` section is required. When a high-stakes signal is present and the section is missing, this step blocks until it is written; a placeholder answer ("TBD") counts as missing.
+Two inputs are read from state and the worktree before writing, not recalled from the conversation: `$WORKTREE/.pipeline/scope-check.json` (Phase 3 Step 3.7) supplies the `## Changes` bullets from `files[].reason` and the "Follow-ups not done in this PR" list under `## Related` from `notDone[]`; `state.diffRisk.signals` (Phase 4 Step 1.75) decides whether the conditional `## Risk and Security` section is required. When a high-stakes signal is present and the section is missing, this step blocks until it is written; a placeholder answer ("TBD") counts as missing. `state.visualEvidence.required` blocks the same way: every required artefact is either attached or carries a recorded reason in `gaps[]` - the gate is against silence, not against an honest "no image on the ticket".
 
 **required**: Run all generated text (PR body, commit message) through the `humanizer` skill before posting. This removes AI-generated patterns (inflated language, filler phrases, repetitive structure) and makes the output sound like a developer wrote it.
 

package/pipeline/multi-agent-refs/phases/phase-7-report.md

@@ -251,7 +251,14 @@ fi
 
 The ledger is JSONL at `~/.claude/memory/multi-agent/<repo-slug>/learnings-ledger.jsonl`, next to the triage corpus, per-repo isolated. Its brief is replayed into Phase 1 analysis and Phase 4 triage on future runs.
 
-Print compact summary to terminal:
+Print the closing report to the terminal. Two blocks, in this order  -  what the pipeline spent, then what it changed:
+
+```bash
+bash $HOME/.claude/scripts/phase-tracker.sh report
+bash $HOME/.claude/scripts/render-work-summary.sh "$TASK_ID" --worktree "$WORKTREE_PATH"
+```
+
+`report` prices the run phase by phase; `render-work-summary.sh` says what changed on disk. Both land in tool output, which the host collapses, so **reprint them in your reply** followed by this line:
 
 ```
 {jiraId} complete

package/pipeline/multi-agent-refs/tracker-contract.md

@@ -103,6 +103,52 @@ For each phase in the current mode, IN PHASE-NUMBER ORDER (0 → 1 → 2 → ...
 
 The `tasklist_id` meta field is persisted so that `:resume` can rebuild the TaskList from the state file in a fresh session.
 
+#### The card is not the widget
+
+`phase-tracker.sh render` prints a bordered ANSI card to stdout, and every
+supported host collapses tool output into a one-line summary (`Ran 8 shell
+commands`). A run whose only progress signal is that card is a run the user
+watches in silence  -  which is exactly what happened: the card was correct on
+disk and invisible on screen.
+
+So each host has a widget, and the tracker names the calls rather than assuming
+the agent remembers them:
+
+| Host | Widget | How it is registered |
+|---|---|---|
+| Claude Code | native TaskList tiles | `TaskCreate` per phase, then `TaskUpdate` per boundary |
+| Codex CLI | native plan steps | one `update_plan` carrying the FULL step list, resent per boundary |
+| Copilot CLI | none exists | the card itself, reprinted inside the agent's reply |
+
+`phase-tracker.sh tiles` prints the registration calls for the host it runs on,
+read from the phase set already registered by `add`. Every `update` then prints
+a `-- NEXT (required) --` block with that host's mirror call and, on completion,
+the narration line built from what was actually recorded. Both are printed to be
+acted on, not read.
+
+#### Accounting is a gate, not a request
+
+`update <N> completed` exits **3** for phases 1-4 when nothing was recorded via
+`tokens`. The alternative is what shipped for months: the docs asked for the
+call, `smoke-tracker-tokens-invocation.sh` linted that the docs *mention* the
+call, and no run made it  -  every phase priced at `-`, every completion line
+printed without numbers, and every gate green. A lint over prose cannot observe
+a runtime omission; the tool that would have received the call can.
+
+The refusal is recoverable and loses no work:
+
+```bash
+phase-tracker.sh model  <N> <model_name>
+phase-tracker.sh tokens <N> <in> <out> [cached]
+phase-tracker.sh update <N> completed
+```
+
+`model` resolves a full model id to its cost-table family (`claude-opus-5` →
+`opus`) and says so out loud when it cannot, because an unpriced name is the
+other way a phase silently costs nothing. A phase that truly ran no LLM call
+completes with `--no-llm`, which is recorded and keeps it out of the run
+report's cost-unavailable list.
+
 #### TaskCreate ordering (strict)
 
 **The native TaskList widget renders tiles in TaskCreate creation order, NOT by phase-number metadata.** Therefore:

package/pipeline/schemas/agent-state.schema.json

@@ -244,7 +244,7 @@
     "onlyDevelop": {
       "type": "boolean",
       "default": false,
-      "description": "Short pipeline  -  phases 1 and 2 are skipped. Set by the Phase 0 Step 7.5 depth picker as of v16.0.0 (it was the --dev flag before); the key and every reader of it are unchanged. Phase 4 Review still runs (v14.0.0+). Always false in an autopilot run, which never asks the depth question."
+      "description": "Short pipeline  -  phases 1 and 2 are skipped. Set by the Phase 0 Step 7.5 depth picker as of v16.0.0; the key and every reader of it are unchanged. Phase 4 Review still runs (v14.0.0+). Always false in an autopilot run, which never asks the depth question."
     },
     "localMode": {
       "type": "boolean",
@@ -272,7 +272,9 @@
         },
         "docPath": {
           "type": "array",
-          "items": { "type": "string" },
+          "items": {
+            "type": "string"
+          },
           "description": "One emitted path per selected platform."
         },
         "frontMatter": {
@@ -604,7 +606,9 @@
             },
             "failing": {
               "type": "array",
-              "items": { "type": "string" },
+              "items": {
+                "type": "string"
+              },
               "description": "Identifiers of tests already failing before this run. Empty on a red status means the output could not be parsed into names: the evidence is then the logPath alone, and Phase 4 reports 'inherited red, not attributable' rather than inventing a set."
             },
             "logPath": {
@@ -655,17 +659,28 @@
             "additionalProperties": true,
             "description": "Written by Phase 4 Step 3.8 from review-delta.mjs: how this round's accepted findings relate to the previous round's rework mandate. Absent on iteration 1 and on runs from before the delta existed.",
             "properties": {
-              "previousIteration": { "type": "integer", "minimum": 1 },
+              "previousIteration": {
+                "type": "integer",
+                "minimum": 1
+              },
               "new": {
                 "type": "array",
                 "items": {
                   "type": "object",
                   "additionalProperties": true,
                   "properties": {
-                    "fingerprint": { "type": "string" },
-                    "severity": { "type": ["string", "null"] },
-                    "file": { "type": ["string", "null"] },
-                    "issue": { "type": ["string", "null"] }
+                    "fingerprint": {
+                      "type": "string"
+                    },
+                    "severity": {
+                      "type": ["string", "null"]
+                    },
+                    "file": {
+                      "type": ["string", "null"]
+                    },
+                    "issue": {
+                      "type": ["string", "null"]
+                    }
                   }
                 }
               },
@@ -675,10 +690,18 @@
                   "type": "object",
                   "additionalProperties": true,
                   "properties": {
-                    "fingerprint": { "type": "string" },
-                    "severity": { "type": ["string", "null"] },
-                    "file": { "type": ["string", "null"] },
-                    "issue": { "type": ["string", "null"] }
+                    "fingerprint": {
+                      "type": "string"
+                    },
+                    "severity": {
+                      "type": ["string", "null"]
+                    },
+                    "file": {
+                      "type": ["string", "null"]
+                    },
+                    "issue": {
+                      "type": ["string", "null"]
+                    }
                   }
                 }
               },
@@ -688,10 +711,18 @@
                   "type": "object",
                   "additionalProperties": true,
                   "properties": {
-                    "fingerprint": { "type": "string" },
-                    "severity": { "type": ["string", "null"] },
-                    "file": { "type": ["string", "null"] },
-                    "issue": { "type": ["string", "null"] }
+                    "fingerprint": {
+                      "type": "string"
+                    },
+                    "severity": {
+                      "type": ["string", "null"]
+                    },
+                    "file": {
+                      "type": ["string", "null"]
+                    },
+                    "issue": {
+                      "type": ["string", "null"]
+                    }
                   }
                 }
               },
@@ -701,10 +732,18 @@
                   "type": "object",
                   "additionalProperties": true,
                   "properties": {
-                    "fingerprint": { "type": "string" },
-                    "severity": { "type": ["string", "null"] },
-                    "file": { "type": ["string", "null"] },
-                    "issue": { "type": ["string", "null"] }
+                    "fingerprint": {
+                      "type": "string"
+                    },
+                    "severity": {
+                      "type": ["string", "null"]
+                    },
+                    "file": {
+                      "type": ["string", "null"]
+                    },
+                    "issue": {
+                      "type": ["string", "null"]
+                    }
                   }
                 }
               },
@@ -714,24 +753,40 @@
                   "type": "object",
                   "additionalProperties": true,
                   "properties": {
-                    "fingerprint": { "type": "string" },
-                    "severity": { "type": ["string", "null"] },
-                    "file": { "type": ["string", "null"] },
-                    "issue": { "type": ["string", "null"] }
+                    "fingerprint": {
+                      "type": "string"
+                    },
+                    "severity": {
+                      "type": ["string", "null"]
+                    },
+                    "file": {
+                      "type": ["string", "null"]
+                    },
+                    "issue": {
+                      "type": ["string", "null"]
+                    }
                   }
                 }
               },
               "recurrence": {
                 "type": "object",
-                "additionalProperties": { "type": "integer", "minimum": 1 },
+                "additionalProperties": {
+                  "type": "integer",
+                  "minimum": 1
+                },
                 "description": "fingerprint -> consecutive rework cycles the finding has survived."
               },
               "plateau": {
                 "type": "boolean",
                 "description": "The still-present set is unchanged from the previous delta and non-empty."
               },
-              "tripped": { "type": "boolean" },
-              "computedAt": { "type": "string", "format": "date-time" }
+              "tripped": {
+                "type": "boolean"
+              },
+              "computedAt": {
+                "type": "string",
+                "format": "date-time"
+              }
             }
           },
           "reviewers": {
@@ -768,7 +823,9 @@
               },
               "labelToModel": {
                 "type": "object",
-                "additionalProperties": { "type": "string" },
+                "additionalProperties": {
+                  "type": "string"
+                },
                 "description": "Source A|B|C -> model name. \"unknown\" for a reviewer entry that declared no model."
               }
             }
@@ -789,25 +846,51 @@
       "description": "Autopilot circuit-breaker record (refs/features/autopilot-circuit-breaker.md). Written only when a trigger trips: trigger 2 by Phase 4 Step 3.8 (a mandate finding survived identicalFindingCycles rework cycles), trigger 3 by the Phase 3 re-entry hard-kill. /multi-agent:resume clears tripped and keeps counters.",
       "required": ["tripped"],
       "properties": {
-        "tripped": { "type": "boolean" },
-        "trigger": { "type": ["integer", "null"], "minimum": 1, "maximum": 5 },
-        "detail": { "type": "string" },
+        "tripped": {
+          "type": "boolean"
+        },
+        "trigger": {
+          "type": ["integer", "null"],
+          "minimum": 1,
+          "maximum": 5
+        },
+        "detail": {
+          "type": "string"
+        },
         "checkpoint": {
           "type": "object",
           "additionalProperties": false,
           "properties": {
-            "phase": { "type": "integer", "minimum": 0, "maximum": 7 },
-            "step": { "type": "string" },
-            "iteration": { "type": "integer", "minimum": 1 }
+            "phase": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 7
+            },
+            "step": {
+              "type": "string"
+            },
+            "iteration": {
+              "type": "integer",
+              "minimum": 1
+            }
           }
         },
-        "trippedAt": { "type": "string", "format": "date-time" },
+        "trippedAt": {
+          "type": "string",
+          "format": "date-time"
+        },
         "counters": {
           "type": "object",
           "additionalProperties": false,
           "properties": {
-            "identicalFindingCycles": { "type": "integer", "minimum": 0 },
-            "reworkCycles": { "type": "integer", "minimum": 0 }
+            "identicalFindingCycles": {
+              "type": "integer",
+              "minimum": 0
+            },
+            "reworkCycles": {
+              "type": "integer",
+              "minimum": 0
+            }
           }
         }
       }
@@ -817,13 +900,26 @@
       "additionalProperties": true,
       "description": "Totals from diff-risk-score.mjs, persisted by Phase 4 Step 1.75 so Phase 6 (PR risk section), Phase 7 and run-metrics.mjs read the same numbers the review scope decision used.",
       "properties": {
-        "files": { "type": "integer", "minimum": 0 },
-        "loc_added": { "type": "integer", "minimum": 0 },
-        "loc_removed": { "type": "integer", "minimum": 0 },
-        "max_score": { "type": "number" },
+        "files": {
+          "type": "integer",
+          "minimum": 0
+        },
+        "loc_added": {
+          "type": "integer",
+          "minimum": 0
+        },
+        "loc_removed": {
+          "type": "integer",
+          "minimum": 0
+        },
+        "max_score": {
+          "type": "number"
+        },
         "signals": {
           "type": "array",
-          "items": { "type": "string" },
+          "items": {
+            "type": "string"
+          },
           "description": "Distinct signal names seen across files (security_path, migration, public_api, no_test_change, test_lines_removed, ...)."
         }
       }
@@ -1001,6 +1097,137 @@
     "artifactsPath": {
       "type": ["string", "null"],
       "description": "Directory the worktree's artefacts were salvaged into before removal (agent-state, phase-tracker, triage-output, .pipeline/, build+test logs, review diff). Phase 7 and :resume read from here when worktreePath is gone."
+    },
+    "visualEvidence": {
+      "type": ["object", "null"],
+      "additionalProperties": false,
+      "description": "Before/after screenshots and the UI flow video for a UI change, attached to the Jira issue and rendered in the Phase 7 comment and the PR body. Required decided mechanically from taskType plus the changed-file list. Contract: multi-agent-refs/features/visual-evidence.md.",
+      "properties": {
+        "required": {
+          "type": "boolean"
+        },
+        "requiredBy": {
+          "type": "string",
+          "description": "Which rule made it required, e.g. 'bugfix + ui-file-changed'."
+        },
+        "platform": {
+          "type": "string",
+          "enum": ["ios", "android", "web", "other"]
+        },
+        "before": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "additionalProperties": true,
+            "properties": {
+              "file": {
+                "type": "string",
+                "description": "Local path under $WORKTREE/.pipeline/evidence/."
+              },
+              "source": {
+                "type": "string",
+                "enum": ["ticket", "capture"]
+              },
+              "capturedAt": {
+                "type": "string",
+                "description": "Phase that produced it, e.g. 'phase-3'."
+              },
+              "jiraFilename": {
+                "type": "string",
+                "description": "Attachment filename the Jira comment references."
+              },
+              "url": {
+                "type": "string",
+                "description": "Jira attachment content URL."
+              }
+            }
+          },
+          "description": "Images taken from the issue's own attachments. The pipeline never rebuilds the pre-fix state to photograph it; no ticket image means no before, recorded as a gap."
+        },
+        "after": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "additionalProperties": true,
+            "properties": {
+              "file": {
+                "type": "string",
+                "description": "Local path under $WORKTREE/.pipeline/evidence/."
+              },
+              "source": {
+                "type": "string",
+                "enum": ["ticket", "capture"]
+              },
+              "capturedAt": {
+                "type": "string",
+                "description": "Phase that produced it, e.g. 'phase-3'."
+              },
+              "jiraFilename": {
+                "type": "string",
+                "description": "Attachment filename the Jira comment references."
+              },
+              "url": {
+                "type": "string",
+                "description": "Jira attachment content URL."
+              }
+            }
+          },
+          "description": "Captured in Phase 3 after the build+test gate, because Phase 5 is dropped by every autopilot and --local entry."
+        },
+        "videoTier": {
+          "type": ["integer", "null"],
+          "enum": [1, 2, 3, null],
+          "description": "1 = the repo's own UI test target drove the flow, 2 = MCP-driven flow, 3 = no runnable build."
+        },
+        "video": {
+          "type": "object",
+          "additionalProperties": true,
+          "properties": {
+            "file": {
+              "type": "string",
+              "description": "Local path under $WORKTREE/.pipeline/evidence/."
+            },
+            "source": {
+              "type": "string",
+              "enum": ["ticket", "capture"]
+            },
+            "capturedAt": {
+              "type": "string",
+              "description": "Phase that produced it, e.g. 'phase-3'."
+            },
+            "jiraFilename": {
+              "type": "string",
+              "description": "Attachment filename the Jira comment references."
+            },
+            "url": {
+              "type": "string",
+              "description": "Jira attachment content URL."
+            },
+            "seconds": {
+              "type": "number",
+              "description": "Recorded duration; capped at 60."
+            }
+          }
+        },
+        "gaps": {
+          "type": "array",
+          "description": "Every artefact that is required and absent, with its reason. A recorded reason satisfies the Phase 6 blocker; silence does not.",
+          "items": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+              "what": {
+                "type": "string",
+                "enum": ["before", "after", "video"]
+              },
+              "reason": {
+                "type": "string"
+              }
+            },
+            "required": ["what", "reason"]
+          }
+        }
+      }
     }
   }
 }